© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6435
    Prev
    Next
    INDEX
    Explanations

    percentage changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes or trends in numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eve
    -0.62
     Centauri
    -0.60
     Founding
    -0.58
     severed
    -0.58
     Eternity
    -0.56
     Fenrir
    -0.56
     Aliens
    -0.56
     Andromeda
    -0.56
    ador
    -0.55
     Portal
    -0.55
    POSITIVE LOGITS
    graded
    1.22
    grading
    1.06
     sharply
    1.02
    grades
    1.02
     marginally
    0.96
     considerably
    0.88
     significantly
    0.84
    raised
    0.84
    regulation
    0.83
    regulated
    0.82
    Activations Density 0.040%

    No Known Activations